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

    Neuronpedia

    INDEX
    Explanations

    verb "to be"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ДК
    -0.06
    ühl
    -0.06
    .gwt
    -0.06
     apprentice
    -0.06
     penalties
    -0.06
    integration
    -0.06
     scratching
    -0.06
    MM
    -0.06
     participants
    -0.06
    rought
    -0.06
    POSITIVE LOGITS
     bisexual
    0.07
     slightly
    0.07
     Ballet
    0.07
    marks
    0.07
    วไป
    0.06
     이러
    0.06
    _outer
    0.06
    ="__
    0.06
     bật
    0.06
     aerospace
    0.06
    Act Density 0.123%

    No Known Activations