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

    Neuronpedia

    INDEX
    Explanations

    user stories

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Secure
    0.56
    TL
    0.52
     оце
    0.52
     CLE
    0.51
     quán
    0.51
    CCL
    0.51
     conform
    0.50
    0.50
    nx
    0.49
    rf
    0.49
    POSITIVE LOGITS
    atórios
    0.74
     relatório
    0.70
     daleko
    0.70
     iliş
    0.68
    atório
    0.67
    opies
    0.67
    ório
    0.66
     kontinu
    0.65
    asjoner
    0.65
     intelekt
    0.64
    Act Density 0.000%

    No Known Activations