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

    Neuronpedia

    INDEX
    Explanations

    fear itself

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     خطر
    0.39
    বিভ
    0.39
    adien
    0.38
    ourcen
    0.38
    ართველ
    0.37
     그러면은
    0.37
     zależ
    0.37
    bergement
    0.37
    onOptions
    0.36
    managerpage
    0.36
    POSITIVE LOGITS
    <0xE2>
    0.43
     Tom
    0.42
     Shi
    0.41
     br
    0.39
     Es
    0.38
     ring
    0.38
     Nick
    0.38
     Sach
    0.38
     Sapp
    0.38
     Force
    0.37
    Act Density 0.001%

    No Known Activations