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

    Neuronpedia

    INDEX
    Explanations

    parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     clutch
    -0.07
    .Toggle
    -0.07
    icles
    -0.06
     Grinder
    -0.06
    CHA
    -0.06
     Testament
    -0.06
    _mark
    -0.06
     discharge
    -0.06
    ToDevice
    -0.06
    .When
    -0.06
    POSITIVE LOGITS
    withErrors
    0.07
     teased
    0.06
     ⓘ
    0.06
     Cialis
    0.06
     :/:
    0.06
    >:</
    0.06
    .AppendLine
    0.06
    _tm
    0.06
    表现
    0.06
    .netflix
    0.06
    Act Density 0.032%

    No Known Activations