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

    Neuronpedia

    INDEX
    Explanations

    First-person pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.06
    812
    -0.06
    ,__
    -0.06
     kole
    -0.06
    го
    -0.06
    umeric
    -0.06
     Story
    -0.06
    }
↵
↵
    -0.06
    avig
    -0.06
    láš
    -0.06
    POSITIVE LOGITS
     Details
    0.07
     mentality
    0.07
     minlength
    0.07
    _ref
    0.06
    症
    0.06
     [,
    0.06
    Blake
    0.06
     SPEED
    0.06
     Honda
    0.06
     prerequisite
    0.06
    Act Density 0.004%

    No Known Activations