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
    jaw
    -0.08
     aValue
    -0.07
    -0.07
    उन
    -0.07
    кового
    -0.07
     dai
    -0.07
     nalez
    -0.07
    urities
    -0.07
    #aa
    -0.06
    xaa
    -0.06
    POSITIVE LOGITS
     Snapshot
    0.07
     Btn
    0.07
    бург
    0.06
     mess
    0.06
     viet
    0.06
     bağ
    0.06
     Consort
    0.06
    Bl
    0.06
    -bg
    0.06
     rainbow
    0.06
    Act Density 0.000%

    No Known Activations