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

    Neuronpedia

    INDEX
    Explanations

    fram

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Parse
    -0.07
     vines
    -0.07
     Nightmare
    -0.06
    抛弃
    -0.06
    Council
    -0.06
    cleanup
    -0.06
    坠
    -0.06
    倒在
    -0.06
    ushed
    -0.06
    种植
    -0.06
    POSITIVE LOGITS
    賓
    0.07
    🤖
    0.07
     Harm
    0.07
     EXT
    0.07
     độc
    0.07
    }';↵
    0.06
     При
    0.06
    _CRITICAL
    0.06
     brass
    0.06
     특
    0.06
    Act Density 0.004%

    No Known Activations