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

    Neuronpedia

    INDEX
    Explanations

    incident reports and observations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     killers
    1.08
     killings
    1.04
     massacre
    1.03
     thugs
    0.96
     killer
    0.96
     murderer
    0.93
     murderous
    0.93
     killing
    0.91
     murders
    0.91
     murderers
    0.89
    POSITIVE LOGITS
     observations
    0.90
     observar
    0.89
     observed
    0.85
     aproximadamente
    0.85
     advise
    0.82
     observa
    0.79
     approximately
    0.79
    observations
    0.78
     громадян
    0.78
     Approximately
    0.77
    Act Density 0.077%

    No Known Activations