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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    publish
    -0.07
    oken
    -0.07
     TRACK
    -0.07
    ług
    -0.06
     escaped
    -0.06
     الآن
    -0.06
    ANI
    -0.06
     publish
    -0.06
     Skipping
    -0.06
    ulen
    -0.06
    POSITIVE LOGITS
     acids
    0.07
    EATURE
    0.07
    Motion
    0.07
    �
    0.06
    .cc
    0.06
    -memory
    0.06
     vampire
    0.06
     eens
    0.06
     Việt
    0.06
    .JsonProperty
    0.06
    Act Density 0.000%

    No Known Activations