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

    Neuronpedia

    INDEX
    Explanations

    something happening soon

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ektiv
    -0.07
    GLuint
    -0.07
    spr
    -0.06
    .mod
    -0.06
    Policy
    -0.06
    Rotate
    -0.06
    -､
    -0.06
    	File
    -0.06
     meaningless
    -0.06
     UD
    -0.06
    POSITIVE LOGITS
    .`|`↵
    0.08
    (movie
    0.07
     zakáz
    0.07
    -facing
    0.07
     активно
    0.06
    _GT
    0.06
     oppose
    0.06
    馬
    0.06
    Heart
    0.06
    -eng
    0.06
    Act Density 0.210%

    No Known Activations