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

    Neuronpedia

    INDEX
    Explanations

    identity theft

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    şil
    0.49
    idences
    0.40
     precludes
    0.40
    ziff
    0.39
    имость
    0.38
    ፫
    0.38
    ניות
    0.37
    けば
    0.36
     PTH
    0.36
     Latte
    0.36
    POSITIVE LOGITS
    𝘬
    0.40
    adr
    0.39
     darkened
    0.38
    AYA
    0.37
     times
    0.36
    aya
    0.36
    arena
    0.35
    jing
    0.34
    seit
    0.33
    getUsername
    0.33
    Act Density 0.000%

    No Known Activations