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

    Neuronpedia

    INDEX
    Explanations

    Ps

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .har
    -0.06
    件事
    -0.06
     Eyes
    -0.06
    ubuntu
    -0.06
    ght
    -0.06
    ancies
    -0.06
    แล
    -0.06
    .list
    -0.06
     ect
    -0.06
    anga
    -0.06
    POSITIVE LOGITS
     widening
    0.07
     Philipp
    0.06
     adlı
    0.06
     ->↵
    0.06
     ΑΠ
    0.06
     firearms
    0.06
    '-
    0.06
    ')↵↵↵
    0.06
    たら
    0.06
    Titan
    0.06
    Act Density 0.003%

    No Known Activations