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

    Neuronpedia

    INDEX
    Explanations

    geographical names and locations

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

    states and cities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ExtendWith
    -0.40
     Peres
    -0.33
    principalTable
    -0.32
    OneToMany
    -0.32
     capacity
    -0.32
    lierten
    -0.31
    classmethod
    -0.30
    器
    -0.30
     „
    -0.29
     loading
    -0.29
    POSITIVE LOGITS
     queſta
    0.63
     verſch
    0.56
     laſſen
    0.54
     ſtate
    0.54
    ſicht
    0.53
     müſſen
    0.52
     fashiola
    0.52
     ftate
    0.52
    linawan
    0.52
    ꔛ
    0.52
    Act Density 0.150%

    No Known Activations