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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ivers
    -0.06
    ちら
    -0.06
    _cookie
    -0.06
    iefs
    -0.06
     findet
    -0.06
    ">(
    -0.06
    Fall
    -0.06
    Phrase
    -0.06
     chiefs
    -0.06
    uding
    -0.06
    POSITIVE LOGITS
    loaded
    0.07
     IntPtr
    0.07
     بشكل
    0.07
     recruited
    0.07
     mandated
    0.07
     enjoyed
    0.07
     subscribed
    0.07
     accepted
    0.07
    VED
    0.07
     explained
    0.07
    Act Density 0.148%

    No Known Activations