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

    Neuronpedia

    INDEX
    Explanations

    unstructured text/code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    WAR
    -0.07
     कई
    -0.06
     admits
    -0.06
    _remaining
    -0.06
    /buttons
    -0.06
     implications
    -0.06
     FAT
    -0.06
    streams
    -0.06
    ailure
    -0.06
    ictim
    -0.06
    POSITIVE LOGITS
     lesbische
    0.07
    _KEYWORD
    0.06
    _instr
    0.06
    edBy
    0.06
     printers
    0.06
     sensory
    0.06
     replay
    0.06
     theolog
    0.06
     breeding
    0.06
    资产
    0.06
    Act Density 0.000%

    No Known Activations