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

    Neuronpedia

    INDEX
    Explanations

    Code syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cessation
    -0.07
    ｩ
    -0.07
    ⛳
    -0.07
    _continue
    -0.07
    基金经理
    -0.07
    不断的
    -0.07
     świat
    -0.07
    .Alpha
    -0.07
     Surely
    -0.07
    好
    -0.06
    POSITIVE LOGITS
     fingerprints
    0.06
     Yard
    0.06
     hollow
    0.06
     ödül
    0.06
     drawings
    0.06
    .expand
    0.06
     gimm
    0.06
     Conditional
    0.06
    伉
    0.06
     discarded
    0.06
    Act Density 0.021%

    No Known Activations