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

    Neuronpedia

    INDEX
    Explanations

    no-obligation offers or quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ’,
    0.63
    ,
    0.60
    ,’
    0.59
    ill
    0.57
    ini
    0.56
    aba
    0.55
    ’
    0.55
    ’)
    0.54
    0
    0.54
    ’.
    0.54
    POSITIVE LOGITS
    فك
    0.69
    انس
    0.68
    LOTREntity
    0.61
    ház
    0.61
    вшись
    0.60
    황
    0.60
     ríg
    0.60
     localVarAccept
    0.59
    اك
    0.59
    焓
    0.59
    Act Density 0.001%

    No Known Activations