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

    Neuronpedia

    INDEX
    Explanations

    Option 1

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PPI
    0.38
    PUR
    0.38
     ха
    0.36
     PUR
    0.35
    ULAR
    0.34
     HA
    0.34
    GIT
    0.34
    Ic
    0.33
    PIL
    0.31
    AUR
    0.31
    POSITIVE LOGITS
     Declan
    0.37
    那位
    0.35
    jmp
    0.33
    jer
    0.33
    有個
    0.33
    카드
    0.33
    ikations
    0.33
    jonen
    0.32
    jero
    0.32
    分隔
    0.32
    Act Density 0.011%

    No Known Activations