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

    Neuronpedia

    INDEX
    Explanations

    Trinity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
    .UI
    -0.07
     değildir
    -0.07
     Jing
    -0.07
     tasting
    -0.06
    iks
    -0.06
    ambda
    -0.06
     main
    -0.06
     octave
    -0.06
     lidí
    -0.06
    POSITIVE LOGITS
     disillusion
    0.07
     ож
    0.07
     subtype
    0.06
    cantidad
    0.06
     �
    0.06
     záz
    0.06
     slowdown
    0.06
    otr
    0.06
    (nome
    0.06
    \xff
    0.06
    Act Density 0.018%

    No Known Activations