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

    Neuronpedia

    INDEX
    Explanations

    safety procedures and resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.59
    hkse
    0.55
    ೆಯಲ್ಲಿ
    0.51
    ʢ
    0.51
    <unused47>
    0.50
     intestine
    0.50
    followlike
    0.49
    ➴
    0.49
    象
    0.48
    hne
    0.47
    POSITIVE LOGITS
    ,
    0.47
    D
    0.46
     chambers
    0.44
     builders
    0.43
     builder
    0.43
    .
    0.43
     D
    0.43
     Chem
    0.43
     concrete
    0.43
     collector
    0.42
    Act Density 0.001%

    No Known Activations