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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .IC
    -0.07
    .Plugin
    -0.07
    ocratic
    -0.07
     joke
    -0.07
     handheld
    -0.06
    JSON
    -0.06
     attendee
    -0.06
    築
    -0.06
    wjgl
    -0.06
    ormal
    -0.06
    POSITIVE LOGITS
     ReferentialAction
    0.06
     depend
    0.06
     prohibit
    0.06
     му
    0.06
    این
    0.06
     virgin
    0.06
     %@",
    0.06
     muối
    0.06
     علیه
    0.06
    いて
    0.06
    Act Density 0.013%

    No Known Activations