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

    Neuronpedia

    INDEX
    Explanations

    risk

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .location
    -0.07
    .proc
    -0.07
    ".$_
    -0.07
    n
    -0.06
    Roboto
    -0.06
    .setAlignment
    -0.06
    .jpa
    -0.06
    adeon
    -0.06
    ัฐ
    -0.06
     expiresIn
    -0.06
    POSITIVE LOGITS
    资源
    0.06
    EEK
    0.06
     IH
    0.06
     Guards
    0.06
    اطق
    0.06
    zell
    0.06
     gå
    0.06
    ress
    0.06
    υγ
    0.06
    优势
    0.06
    Act Density 0.008%

    No Known Activations