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

    Neuronpedia

    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     modules
    -0.07
     seasons
    -0.07
     Apart
    -0.07
    Fin
    -0.06
    _:
    -0.06
     cola
    -0.06
     peers
    -0.06
     commands
    -0.06
    izi
    -0.06
     dich
    -0.06
    POSITIVE LOGITS
    ToUpdate
    0.07
    ikt
    0.06
    KG
    0.06
     handleSubmit
    0.06
     keto
    0.06
    URNS
    0.06
     phúc
    0.06
    atively
    0.06
     Nottingham
    0.06
    <State
    0.06
    Act Density 0.006%

    No Known Activations