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

    Neuronpedia

    INDEX
    Explanations

    verbs related to performance or behavior

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

    act like, in, of, Accordingly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    getahuan
    -0.39
    simple
    -0.38
    Simple
    -0.38
    encontra
    -0.38
     information
    -0.38
     anteriormente
    -0.36
     yh
    -0.36
     justiça
    -0.35
     Simple
    -0.35
     threshold
    -0.35
    POSITIVE LOGITS
     Мексичка
    0.58
     stunts
    0.54
     utafitiHapana
    0.54
    0.53
     behave
    0.53
    Act
    0.53
     Infórmanos
    0.53
    act
    0.52
     queſta
    0.52
    +#+
    0.51
    Act Density 0.009%

    No Known Activations