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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kills
    -0.06
     Killer
    -0.06
    帝国
    -0.06
    .getConfig
    -0.06
     '/',
    -0.06
    ชาว
    -0.06
     findBy
    -0.06
    defines
    -0.06
    альном
    -0.06
    .dataset
    -0.06
    POSITIVE LOGITS
     apology
    0.06
     invitations
    0.06
    Union
    0.06
     understand
    0.06
     disagree
    0.06
    CLEAR
    0.06
     astonished
    0.06
     honoured
    0.06
    #index
    0.06
    cess
    0.06
    Act Density 0.024%

    No Known Activations