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

    Neuronpedia

    INDEX
    Explanations

    projection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dark
    -0.06
     entert
    -0.06
    _fixed
    -0.06
    Except
    -0.06
    _SB
    -0.06
    bp
    -0.06
     wild
    -0.06
    failure
    -0.06
     slavery
    -0.06
    ÜM
    -0.06
    POSITIVE LOGITS
     projection
    0.08
    iểu
    0.07
    투
    0.07
    .eps
    0.07
    Projection
    0.07
    ←
    0.07
    θεια
    0.07
    hung
    0.06
     lends
    0.06
     lions
    0.06
    Act Density 0.002%

    No Known Activations