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

    Neuronpedia

    INDEX
    Explanations

    stored

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    59
    -0.07
     Commission
    -0.07
    itesse
    -0.06
     Today
    -0.06
     Andrew
    -0.06
     Lund
    -0.06
     dips
    -0.06
    Eight
    -0.06
    "
    -0.06
    alle
    -0.06
    POSITIVE LOGITS
    .basic
    0.07
    Pref
    0.06
     Boolean
    0.06
    ::↵↵
    0.06
    Acts
    0.06
    (UINT
    0.06
     ल
    0.06
    prepend
    0.06
    зы
    0.06
     klar
    0.05
    Act Density 0.040%

    No Known Activations