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

    Neuronpedia

    INDEX
    Explanations

    Explosions and fire hazards

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     grav
    -0.07
    -co
    -0.06
    津
    -0.06
    +v
    -0.06
     المك
    -0.06
    ха
    -0.06
     ATA
    -0.06
     STAT
    -0.06
     раск
    -0.06
    -he
    -0.06
    POSITIVE LOGITS
    (clicked
    0.07
    )="
    0.06
    mpl
    0.06
    whether
    0.06
    .／
    0.06
     відбува
    0.06
    ือ
    0.06
    _VERIFY
    0.06
    actory
    0.06
    odont
    0.06
    Act Density 0.033%

    No Known Activations