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

    Neuronpedia

    INDEX
    Explanations

    ene

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Shaft
    -0.07
    iors
    -0.06
     paddingRight
    -0.06
    Past
    -0.06
    _successful
    -0.06
     فال
    -0.06
     Mitarbeiter
    -0.06
    viar
    -0.06
    _indent
    -0.06
    маз
    -0.06
    POSITIVE LOGITS
     graphene
    0.13
    cycles
    0.08
    _CHARACTER
    0.08
     exacerbated
    0.07
     deutsche
    0.07
    rage
    0.07
    ampoline
    0.07
     hran
    0.06
    ,E
    0.06
    _UNS
    0.06
    Act Density 0.001%

    No Known Activations