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

    Neuronpedia

    INDEX
    Explanations

    flow

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fol
    -0.07
    察
    -0.06
    Hidden
    -0.06
     Media
    -0.06
     xảy
    -0.06
    texts
    -0.06
     sunny
    -0.06
    									↵
    -0.06
     Metal
    -0.06
    205
    -0.06
    POSITIVE LOGITS
    -full
    0.07
     warranties
    0.07
     noss
    0.06
    .swap
    0.06
    _second
    0.06
    }}</
    0.06
     Consult
    0.06
    }</
    0.06
     comet
    0.06
     defenseman
    0.06
    Act Density 0.018%

    No Known Activations