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

    Neuronpedia

    INDEX
    Explanations

    Providing answers and examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Mat
    0.48
     Mat
    0.44
    Proof
    0.41
    ≐
    0.40
    ро
    0.40
     theorems
    0.40
    هو
    0.40
    та
    0.39
    }$
    0.39
     instructive
    0.38
    POSITIVE LOGITS
     ГӀ
    0.44
     ਤੋਂ
    0.40
    棭
    0.39
    ᅪ
    0.39
    isierten
    0.39
    :'',
    0.39
    ᅦ
    0.39
    féle
    0.38
     डीआर
    0.38
     будущего
    0.37
    Act Density 0.001%

    No Known Activations