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

    Neuronpedia

    INDEX
    Explanations

    logo

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Private
    -0.06
     tension
    -0.06
     PUBLIC
    -0.06
     predator
    -0.06
    _question
    -0.06
    ンジ
    -0.06
     thriller
    -0.06
     Write
    -0.06
    month
    -0.06
    .members
    -0.06
    POSITIVE LOGITS
    XL
    0.07
    ahi
    0.07
    _Ref
    0.07
     metam
    0.07
    LP
    0.07
     лов
    0.07
     Mojo
    0.07
    MO
    0.07
    их
    0.07
     Trudeau
    0.07
    Act Density 0.006%

    No Known Activations