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

    Neuronpedia

    INDEX
    Explanations

    code and text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rieben
    -0.07
    voie
    -0.07
    asso
    -0.07
    neys
    -0.06
    akah
    -0.06
    455
    -0.06
     copp
    -0.06
    opia
    -0.06
    masters
    -0.06
     hangs
    -0.06
    POSITIVE LOGITS
    .Unique
    0.08
    .green
    0.07
    .normalized
    0.07
    .Power
    0.07
    อน
    0.07
    orgt
    0.06
     Максим
    0.06
     genetic
    0.06
    	Input
    0.06
    omit
    0.06
    Act Density 0.000%

    No Known Activations