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

    Neuronpedia

    INDEX
    Explanations

    portions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Yes
    -0.06
    えて
    -0.06
     clinical
    -0.06
    bench
    -0.06
     Diff
    -0.06
    Pressed
    -0.06
     happened
    -0.06
     υπάρχ
    -0.06
     neb
    -0.06
     fourteen
    -0.06
    POSITIVE LOGITS
    (weights
    0.07
    _region
    0.07
     acct
    0.06
     Northeast
    0.06
    凯
    0.06
    .Sqrt
    0.06
    uckle
    0.06
    _Pr
    0.06
     Sk
    0.06
    .Throws
    0.06
    Act Density 0.000%

    No Known Activations