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

    Neuronpedia

    INDEX
    Explanations

    d

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Мар
    -0.06
    _ll
    -0.06
     strained
    -0.06
     empres
    -0.06
    tt
    -0.06
     галуз
    -0.06
    (field
    -0.06
     Personality
    -0.05
     validating
    -0.05
    _forward
    -0.05
    POSITIVE LOGITS
    祥
    0.07
    Emb
    0.07
    坚
    0.07
     Dund
    0.07
    Ν
    0.06
    interrupt
    0.06
    OptionsMenu
    0.06
    ==='
    0.06
     asked
    0.06
    ภาพยนตร
    0.06
    Act Density 0.005%

    No Known Activations