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

    Neuronpedia

    INDEX
    Explanations

    inspecting and reporting data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Filters
    0.40
     ফলো
    0.39
    玝
    0.38
     रहना
    0.36
     Filters
    0.36
    Parameters
    0.36
    సుకోవ
    0.35
     общего
    0.35
    ])+
    0.35
     setDefault
    0.34
    POSITIVE LOGITS
    ToString
    0.84
    toString
    0.84
    ToStr
    0.71
     ToString
    0.68
    Dumper
    0.64
     dump
    0.63
     toString
    0.63
    dump
    0.62
     pformat
    0.60
    inspect
    0.59
    Act Density 0.020%

    No Known Activations