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

    Neuronpedia

    INDEX
    Explanations

    scoring goals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    NotExist
    -0.06
    -cap
    -0.06
    _ins
    -0.06
     Starts
    -0.06
     Olympic
    -0.06
     develops
    -0.06
    ービ
    -0.06
    Msp
    -0.06
    _Final
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    Michelle
    0.08
     Secret
    0.07
     luaL
    0.07
     FIELD
    0.07
    (remove
    0.07
     elle
    0.07
     ¦
    0.07
    Secret
    0.06
     λο
    0.06
    CppI
    0.06
    Act Density 0.016%

    No Known Activations