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

    Neuronpedia

    INDEX
    Explanations

    identifiable + ability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ография
    0.53
    OGRAPHY
    0.51
    ionalmente
    0.50
    льные
    0.49
    чных
    0.49
    नात्मक
    0.48
    OLOGIA
    0.48
    udarstvennyj
    0.47
    жный
    0.47
    ственной
    0.47
    POSITIVE LOGITS
    ag
    0.47
    or
    0.40
    u
    0.39
    ar
    0.38
    '.
    0.38
    az
    0.38
    ".
    0.38
     .
    0.37
    iz
    0.36
    !
    0.36
    Act Density 0.279%

    No Known Activations