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

    Neuronpedia

    INDEX
    Explanations

    underscore

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Battlefield
    -0.07
     impulse
    -0.07
    -story
    -0.07
    Level
    -0.06
     gallons
    -0.06
    Captain
    -0.06
    esktop
    -0.06
    alarm
    -0.06
    avo
    -0.06
     ski
    -0.06
    POSITIVE LOGITS
    _via
    0.08
     FUNCT
    0.08
    _ERRORS
    0.07
    ↵
    0.07
    锊
    0.07
     방
    0.07
    自然是
    0.07
    卺
    0.07
    ，
    0.07
     ISR
    0.06
    Act Density 0.571%

    No Known Activations