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

    Neuronpedia

    INDEX
    Explanations

    punitive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Waves
    -0.08
    �
    -0.07
    _motion
    -0.07
    _instruction
    -0.07
     uomo
    -0.07
    States
    -0.07
    وپ
    -0.06
    Parsed
    -0.06
    스타
    -0.06
     пот
    -0.06
    POSITIVE LOGITS
     punitive
    0.10
    .dtp
    0.07
     lecture
    0.07
     ensure
    0.06
     rethink
    0.06
    .MEDIA
    0.06
    athi
    0.06
     prefers
    0.06
    Party
    0.06
     advises
    0.06
    Act Density 0.000%

    No Known Activations