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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .bo
    -0.07
     Ethiopian
    -0.06
    	case
    -0.06
    後
    -0.06
     Earlier
    -0.06
     deze
    -0.06
    	DB
    -0.06
    ']]],↵
    -0.06
     deceased
    -0.06
    	void
    -0.06
    POSITIVE LOGITS
    １０
    0.07
    něm
    0.06
    _SELF
    0.06
    STAT
    0.06
    zf
    0.06
    _SWAP
    0.06
    opp
    0.06
    _CLOSED
    0.06
    haven
    0.05
     Web
    0.05
    Act Density 0.032%

    No Known Activations