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

    Neuronpedia

    INDEX
    Explanations

    offense

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chains
    -0.07
     determination
    -0.07
    /graph
    -0.07
     جای
    -0.07
     impact
    -0.07
     kuru
    -0.07
    .channel
    -0.07
     �
    -0.07
     Yug
    -0.07
    .collect
    -0.06
    POSITIVE LOGITS
     offense
    0.12
     offenses
    0.11
     offences
    0.11
     offended
    0.10
     offence
    0.10
     offender
    0.08
     Hoffman
    0.08
    ––
    0.07
     offenders
    0.07
    <Texture
    0.07
    Act Density 0.004%

    No Known Activations