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

    Neuronpedia

    INDEX
    Explanations

    organization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Mod
    -0.07
    study
    -0.06
    RequestBody
    -0.06
     defenders
    -0.06
    'є
    -0.06
     گفته
    -0.06
    Leap
    -0.06
    aha
    -0.06
    	count
    -0.06
     sexual
    -0.06
    POSITIVE LOGITS
     pellets
    0.07
     json
    0.06
    ϊ
    0.06
    -cloud
    0.06
    _PARTITION
    0.06
     رج
    0.06
    .chars
    0.06
     Fly
    0.06
     soğ
    0.06
    ORG
    0.06
    Act Density 0.002%

    No Known Activations