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

    Neuronpedia

    INDEX
    Explanations

    maze dimensions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     अवेलेबल
    0.37
    paying
    0.36
     பாதுகாக்க
    0.36
     Saratoga
    0.35
     औसत
    0.35
    Ûn
    0.33
     bañ
    0.33
     pagare
    0.33
     पैदल
    0.33
     Theorie
    0.33
    POSITIVE LOGITS
    Inverse
    0.38
    Definition
    0.36
    Iterator
    0.35
    Interrupt
    0.35
     lspace
    0.35
     kernel
    0.34
    Integral
    0.34
     を
    0.34
     activation
    0.34
    Inline
    0.34
    Act Density 0.000%

    No Known Activations