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

    Neuronpedia

    INDEX
    Explanations

    distinguishing situations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    іє
    -0.07
    lığın
    -0.07
    sez
    -0.06
     Reds
    -0.06
    یزی
    -0.06
    ango
    -0.06
     Reporter
    -0.06
     trace
    -0.06
    363
    -0.06
    _throw
    -0.06
    POSITIVE LOGITS
     ठ
    0.06
     donor
    0.06
    ozy
    0.06
     Diff
    0.06
     moderators
    0.06
     М
    0.06
     Operator
    0.05
    ानव
    0.05
     acted
    0.05
    ==↵
    0.05
    Act Density 0.043%

    No Known Activations