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

    Neuronpedia

    INDEX
    Explanations

    actions, senses, capabilities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ="../../../
    -0.07
    APTER
    -0.07
     io
    -0.07
     nuestra
    -0.06
    ModelProperty
    -0.06
    errs
    -0.06
     Savior
    -0.06
     Graph
    -0.06
     Stadium
    -0.06
    urrencies
    -0.06
    POSITIVE LOGITS
     Ham
    0.06
     درجة
    0.06
    cookies
    0.06
     motif
    0.06
    sand
    0.06
    _pemb
    0.06
    OKIE
    0.06
     поль
    0.06
     shine
    0.06
     scouts
    0.06
    Act Density 0.426%

    No Known Activations