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

    Neuronpedia

    INDEX
    Explanations

    well followed by a pause

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     plików
    0.63
     pytanie
    0.61
     इंपॉर्ट
    0.58
     plufieurs
    0.56
     Oké
    0.55
     béton
    0.54
     Київ
    0.53
     vấn
    0.52
     solides
    0.52
     gonflement
    0.52
    POSITIVE LOGITS
     Certainly
    0.48
    ā
    0.47
    अर्
    0.46
    agence
    0.46
    ında
    0.45
    สเตอร์
    0.45
    aper
    0.45
     certainly
    0.45
    し
    0.45
    uristic
    0.44
    Act Density 0.005%

    No Known Activations