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

    Neuronpedia

    INDEX
    Explanations

    self comparison

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     То
    -0.07
     Budd
    -0.06
    byter
    -0.06
     Ар
    -0.06
     lider
    -0.06
    пня
    -0.06
    territ
    -0.06
    ์)
    -0.06
    ceptions
    -0.06
    (strtolower
    -0.06
    POSITIVE LOGITS
     conv
    0.07
    selectorMethod
    0.06
     somew
    0.06
     hundreds
    0.06
     uni
    0.06
    NameValuePair
    0.06
     apa
    0.06
     mt
    0.06
    (""))↵
    0.06
    Can
    0.06
    Act Density 0.013%

    No Known Activations