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

    Neuronpedia

    INDEX
    Explanations

    Schema and protocol definitions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sval
    -0.09
    AGA
    -0.08
    Activated
    -0.08
    ู้
    -0.08
     Selenium
    -0.08
     Copp
    -0.08
     occupants
    -0.08
    activated
    -0.08
     Mar
    -0.07
    _SELECTOR
    -0.07
    POSITIVE LOGITS
    _yaml
    0.08
     conmigo
    0.08
     YAML
    0.08
    文件
    0.08
     erstellt
    0.08
    Yaml
    0.08
    版权
    0.08
     yacc
    0.08
     파일
    0.08
    BUILD
    0.08
    Act Density 0.005%

    No Known Activations