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

    Neuronpedia

    INDEX
    Explanations

    argument structure or justification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    an
    0.59
    ان
    0.52
    alities
    0.52
    T
    0.52
    지
    0.51
     अग
    0.50
    three
    0.50
    March
    0.48
    ions
    0.48
    iennent
    0.47
    POSITIVE LOGITS
     τόσο
    0.51
    帶
    0.48
    itação
    0.46
     contrô
    0.45
     récup
    0.45
    nění
    0.45
     baix
    0.44
    idação
    0.44
     câu
    0.44
     Tired
    0.44
    Act Density 0.000%

    No Known Activations