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

    Neuronpedia

    INDEX
    Explanations

    but

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .NewReader
    -0.09
    。「
    -0.07
    氿
    -0.07
    谞
    -0.07
    扫一
    -0.07
    ♍
    -0.07
    .ResponseEntity
    -0.07
    enville
    -0.07
    .SEVER
    -0.07
    ערכים
    -0.07
    POSITIVE LOGITS
    deb
    0.07
    ❋
    0.07
    عادة
    0.07
     Jake
    0.07
     pushing
    0.07
    吱
    0.07
     crises
    0.07
     advisor
    0.06
    _CLI
    0.06
     LM
    0.06
    Act Density 0.059%

    No Known Activations