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

    Neuronpedia

    INDEX
    Explanations

    Conversational first-person

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Msg
    -0.07
    _altern
    -0.07
    케
    -0.06
    �
    -0.06
     свеж
    -0.06
    .getType
    -0.06
    roy
    -0.06
     اقتص
    -0.06
     curled
    -0.06
    ουμε
    -0.06
    POSITIVE LOGITS
     Indices
    0.07
    remely
    0.06
     Dank
    0.06
    .special
    0.06
    ами
    0.06
    /shared
    0.06
     складі
    0.06
    (Il
    0.06
     خانم
    0.06
    _SYS
    0.06
    Act Density 0.604%

    No Known Activations