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

    Neuronpedia

    INDEX
    Explanations

    "ment" substring

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cosmic
    -0.07
     gol
    -0.07
     nextProps
    -0.07
     Glo
    -0.07
     CPC
    -0.07
     Health
    -0.07
     CZ
    -0.07
    1
    -0.07
     matplotlib
    -0.07
    /py
    -0.06
    POSITIVE LOGITS
    attachment
    0.07
    emb
    0.07
    estead
    0.07
    sert
    0.06
    wins
    0.06
    NOW
    0.06
    Keith
    0.06
    �
    0.06
    assigned
    0.06
    мат
    0.06
    Act Density 0.005%

    No Known Activations