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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (DE
    -0.07
    cimal
    -0.07
    يق
    -0.07
    enny
    -0.06
    ONG
    -0.06
     contro
    -0.06
    ONY
    -0.06
    ्वय
    -0.06
     loud
    -0.06
    mb
    -0.06
    POSITIVE LOGITS
    /The
    0.07
    /octet
    0.07
    します
    0.06
    _UNSUPPORTED
    0.06
     Peygamber
    0.06
    Making
    0.06
     assertFalse
    0.06
     Sınıf
    0.06
     Pavel
    0.06
    Decrypt
    0.06
    Act Density 0.036%

    No Known Activations