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

    Neuronpedia

    INDEX
    Explanations

    83

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (strpos
    -0.08
     třet
    -0.07
     深
    -0.07
    Owned
    -0.06
    ีเม
    -0.06
    mys
    -0.06
    _project
    -0.05
    bage
    -0.05
    스로
    -0.05
    Davis
    -0.05
    POSITIVE LOGITS
    ournals
    0.07
    CH
    0.07
    614
    0.07
     policing
    0.07
    Atom
    0.07
     cocks
    0.07
     feud
    0.07
     Đặc
    0.07
     LATIN
    0.07
    162
    0.07
    Act Density 0.000%

    No Known Activations