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

    Neuronpedia

    INDEX
    Explanations

    formal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    RET
    -0.07
    ební
    -0.07
     LEFT
    -0.06
    EMS
    -0.06
    _mapper
    -0.06
     forgiven
    -0.06
     transgender
    -0.06
     Qed
    -0.06
    WE
    -0.06
    ネル
    -0.06
    POSITIVE LOGITS
    [counter
    0.07
     coronary
    0.07
    pest
    0.07
     đô
    0.06
    	payload
    0.06
    _dd
    0.06
    sample
    0.06
    施工
    0.06
    你们
    0.06
    .Green
    0.06
    Act Density 0.000%

    No Known Activations