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

    Neuronpedia

    INDEX
    Explanations

    Uncommon words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    高い
    -0.07
    .lib
    -0.07
     suffering
    -0.07
    ecure
    -0.07
    	actual
    -0.07
    _POINTS
    -0.06
    Access
    -0.06
     ölçüde
    -0.06
    _context
    -0.06
     deadline
    -0.06
    POSITIVE LOGITS
     JACK
    0.07
     Созд
    0.06
     Zionist
    0.06
     кл
    0.06
     отли
    0.06
    .unsqueeze
    0.06
    VML
    0.06
    č
    0.06
     предназнач
    0.06
     menacing
    0.06
    Act Density 0.006%

    No Known Activations