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

    Neuronpedia

    INDEX
    Explanations

    disclaimers and advice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Gradient
    -0.07
    ροχή
    -0.06
    fila
    -0.06
    πτυ
    -0.06
    ामक
    -0.06
     :=
    -0.06
    =d
    -0.06
     yarış
    -0.06
    =id
    -0.06
    ,address
    -0.06
    POSITIVE LOGITS
     repos
    0.06
     motif
    0.06
     gates
    0.06
    emin
    0.06
    害
    0.06
     layoutManager
    0.06
     motifs
    0.06
     merely
    0.06
    _lite
    0.06
    .owner
    0.06
    Act Density 0.022%

    No Known Activations