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

    Neuronpedia

    INDEX
    Explanations

    content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ில
    -0.08
     Gill
    -0.08
     atrás
    -0.08
    فيض
    -0.07
     değiş
    -0.07
     Certain
    -0.07
    .changed
    -0.07
     →↵↵
    -0.07
    ита
    -0.07
     Cambio
    -0.07
    POSITIVE LOGITS
     perpetr
    0.09
     wrongdoing
    0.09
     blockade
    0.08
    开奖
    0.08
     outcomes
    0.08
    authorize
    0.08
    Ontology
    0.08
     occupation
    0.08
     leg
    0.08
     mechanics
    0.07
    Act Density 0.026%

    No Known Activations