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

    Neuronpedia

    INDEX
    Explanations

    list items and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     arrondissement
    0.30
     uniaxial
    0.26
     aldehydes
    0.26
    نساء
    0.25
     basaltes
    0.25
    𒆤
    0.25
    ាម
    0.25
     wax
    0.25
     médicos
    0.24
    Pyrazole
    0.24
    POSITIVE LOGITS
    ı
    0.33
     *
    0.33
    eter
    0.33
    0.31
    other
    0.31
    ando
    0.31
    )$
    0.30
    í
    0.28
         
    0.28
    其他
    0.28
    Act Density 0.825%

    No Known Activations