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

    Neuronpedia

    INDEX
    Explanations

    Boosting Regression

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    㨁
    0.48
    㩽
    0.47
    ца
    0.47
    ScriptBuf
    0.47
    ∑</
    0.46
    栘
    0.46
     растения
    0.45
    ட்டு
    0.45
     būti
    0.45
     pů
    0.44
    POSITIVE LOGITS
    Honeycomb
    0.49
    ,
    0.48
     Sail
    0.44
    Haw
    0.40
     in
    0.39
     e
    0.39
     We
    0.39
    Ec
    0.39
    DM
    0.39
    We
    0.38
    Act Density 0.003%

    No Known Activations