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

    Neuronpedia

    INDEX
    Explanations

    Show appearances

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rotating
    -0.07
     UV
    -0.07
     woods
    -0.07
     whe
    -0.06
    (pp
    -0.06
     mistaken
    -0.06
     Rising
    -0.06
     obedience
    -0.06
    _GEN
    -0.06
     ATH
    -0.06
    POSITIVE LOGITS
    toggle
    0.07
    ա
    0.06
    Destination
    0.06
     demolition
    0.06
     scriptures
    0.06
    \Field
    0.06
     datingside
    0.06
     basit
    0.06
    定的
    0.06
    Logo
    0.06
    Act Density 0.069%

    No Known Activations