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

    Neuronpedia

    INDEX
    Explanations

    player

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     retrospective
    -0.06
     values
    -0.06
    ่น
    -0.06
     yük
    -0.06
     delivering
    -0.06
     imaging
    -0.06
     Kubernetes
    -0.06
    clearfix
    -0.06
    _calls
    -0.06
    _google
    -0.06
    POSITIVE LOGITS
     піс
    0.07
    ISMATCH
    0.07
    Hello
    0.07
    prt
    0.06
    .Login
    0.06
     Interview
    0.06
    吾
    0.06
     mixture
    0.06
     mozilla
    0.06
    piel
    0.06
    Act Density 0.018%

    No Known Activations