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

    Neuronpedia

    INDEX
    Explanations

    file paths and programming commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gameplay
    0.71
     internals
    0.60
     context
    0.58
     priorit
    0.57
     rapporte
    0.57
     design
    0.56
     a
    0.55
     fully
    0.55
     wording
    0.55
     omnichannel
    0.54
    POSITIVE LOGITS
     unteren
    0.58
     연습
    0.57
     esperanza
    0.56
    esri
    0.55
    сибир
    0.54
     junio
    0.54
    อยาก
    0.54
    Palindrome
    0.54
     resistenza
    0.54
     resistencias
    0.54
    Act Density 0.117%

    No Known Activations