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

    Neuronpedia

    INDEX
    Explanations

    Adam and Eve

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dirty
    -0.08
    Right
    -0.07
    forest
    -0.07
    named
    -0.07
    _keys
    -0.07
     twins
    -0.07
     growers
    -0.07
     dma
    -0.06
    yellow
    -0.06
     philippines
    -0.06
    POSITIVE LOGITS
    _statuses
    0.07
     nous
    0.06
     inconsist
    0.06
     RTWF
    0.06
     indul
    0.06
    coords
    0.06
    /Subthreshold
    0.06
    .contrib
    0.06
    ург
    0.06
    獎
    0.06
    Act Density 0.043%

    No Known Activations