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

    Neuronpedia

    INDEX
    Explanations

    from, of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     encompasses
    -0.07
     дан
    -0.07
     Brain
    -0.07
     '=',
    -0.07
     katı
    -0.07
     raw
    -0.07
     delt
    -0.07
     शत
    -0.06
     Qt
    -0.06
     coming
    -0.06
    POSITIVE LOGITS
    SetBranchAddress
    0.07
    MES
    0.07
    indeki
    0.06
    ipv
    0.06
     演
    0.06
     grotes
    0.06
    _rent
    0.06
    .Verify
    0.06
     во
    0.06
    local
    0.06
    Act Density 0.010%

    No Known Activations