Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    complex character and plot dynamics in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    defeating an enemy

    np_acts-logits-general · gemini-2.0-flash

    destroy, defeat, surpass, acquire

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Rambo
    -0.58
     Eskimo
    -0.55
     Moslem
    -0.54
     Hust
    -0.54
     ")");
    -0.53
    EndContext
    -0.52
     [@
    -0.51
     beleid
    -0.49
     Philist
    -0.49
    gants
    -0.49
    POSITIVE LOGITS
     powers
    0.65
    Portail
    0.64
    AutoScale
    0.62
    protoimpl
    0.62
     sentient
    0.62
    wikia
    0.62
     humans
    0.61
     missions
    0.59
    aarrggbb
    0.59
     weakened
    0.59
    Act Density 0.746%

    No Known Activations