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

    Neuronpedia

    INDEX
    Explanations

    Describing qualities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gonz
    -0.07
     annot
    -0.07
    ources
    -0.07
     �
    -0.07
     внеш
    -0.07
    .message
    -0.07
    ionato
    -0.07
     vraiment
    -0.07
    GRAPH
    -0.07
     необ
    -0.07
    POSITIVE LOGITS
     hingegen
    0.11
     ones
    0.10
    则
    0.10
     counterpart
    0.10
     మాత్రం
    0.09
    則
    0.09
     naman
    0.08
     Ones
    0.08
    Tet
    0.08
     counterparts
    0.08
    Act Density 0.502%

    No Known Activations