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

    Neuronpedia

    INDEX
    Explanations

    here's a detailed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     просты
    0.40
    cycle
    0.39
    essentially
    0.38
    occur
    0.38
    oldi
    0.38
    Bigr
    0.38
     occur
    0.36
    bler
    0.36
    換え
    0.36
     هغه
    0.36
    POSITIVE LOGITS
     doj
    0.40
    点的
    0.38
     ยาว
    0.37
     Temporary
    0.37
     జాగ
    0.36
     لج
    0.35
     Tenggara
    0.35
     destro
    0.35
    Temporary
    0.35
     caveats
    0.35
    Act Density 0.011%

    No Known Activations