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

    Neuronpedia

    INDEX
    Explanations

    possessive/first-person pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    illac
    -0.07
    _bits
    -0.07
    Difference
    -0.07
     Enhancement
    -0.07
    -hand
    -0.07
     Singular
    -0.07
     selecting
    -0.06
    weed
    -0.06
    -adjust
    -0.06
     empowerment
    -0.06
    POSITIVE LOGITS
     Poz
    0.07
     miền
    0.07
    getDoctrine
    0.06
     ช
    0.06
     Lansing
    0.06
     zih
    0.06
     sheriff
    0.06
    '
↵
↵
    0.06
     muff
    0.06
     congregation
    0.06
    Act Density 0.042%

    No Known Activations