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
    angi
    -0.07
     compressed
    -0.07
    maz
    -0.07
    Drug
    -0.06
     Overse
    -0.06
     encourages
    -0.06
    chemical
    -0.06
     Candidate
    -0.06
     bothering
    -0.06
     pioneering
    -0.06
    POSITIVE LOGITS
    น
    0.06
    震
    0.06
     демон
    0.06
    La
    0.06
     libido
    0.06
    �
    0.06
    COOKIE
    0.06
    dro
    0.06
    طال
    0.06
    три
    0.06
    Act Density 0.075%

    No Known Activations