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

    Neuronpedia

    INDEX
    Explanations

    Comic book battles and powers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Observation
    -0.07
    OWL
    -0.06
    kl
    -0.06
    守
    -0.06
    opez
    -0.06
    scription
    -0.06
     sled
    -0.06
     exporters
    -0.06
    ιος
    -0.06
     operation
    -0.06
    POSITIVE LOGITS
    clide
    0.07
    _geom
    0.06
    +="
    0.06
     кишеч
    0.06
    :numel
    0.06
    /stdc
    0.06
     دول
    0.06
     disb
    0.06
     disputed
    0.06
    _singular
    0.06
    Act Density 0.029%

    No Known Activations