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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _character
    -0.07
     similarity
    -0.07
     wolves
    -0.07
     امکان
    -0.06
     argues
    -0.06
    올
    -0.06
     Cluster
    -0.06
     dangers
    -0.06
    design
    -0.06
    params
    -0.06
    POSITIVE LOGITS
     surrendered
    0.07
    dbg
    0.06
    niční
    0.06
    abcdefghijkl
    0.06
    /inc
    0.06
     京
    0.06
    LETTE
    0.06
    (Messages
    0.06
    owa
    0.06
    dí
    0.06
    Act Density 0.010%

    No Known Activations