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

    Neuronpedia

    INDEX
    Explanations

    failed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Color
    -0.06
    知道
    -0.06
    ัญญ
    -0.06
    iclass
    -0.06
    hton
    -0.06
    ocolate
    -0.06
    _CERT
    -0.06
    _instr
    -0.06
     quantity
    -0.06
    -char
    -0.06
    POSITIVE LOGITS
    Failed
    0.09
    	ID
    0.09
    failed
    0.08
    _failed
    0.08
     podařilo
    0.07
     Failed
    0.07
    [ID
    0.07
    _FAILED
    0.07
    )↵↵
    0.07
    .Typed
    0.07
    Act Density 0.005%

    No Known Activations