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

    Neuronpedia

    INDEX
    Explanations

    victims

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ार
    -0.07
     Manitoba
    -0.06
    seau
    -0.06
    teborg
    -0.06
     JMenuItem
    -0.06
    ElapsedTime
    -0.06
    endforeach
    -0.06
    ffield
    -0.06
    Russia
    -0.06
    enumerate
    -0.06
    POSITIVE LOGITS
     victims
    0.33
     Victims
    0.18
     victim
    0.15
     Victim
    0.12
    victim
    0.12
    _VERIFY
    0.08
    ictim
    0.07
     antib
    0.07
     client
    0.07
    trib
    0.07
    Act Density 0.004%

    No Known Activations