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

    Neuronpedia

    INDEX
    Explanations

    report results

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ste
    -0.07
    atori
    -0.07
     PE
    -0.07
     wiki
    -0.07
    difference
    -0.07
    iagnostics
    -0.07
     persistence
    -0.07
    桓
    -0.07
     Mish
    -0.07
    Targets
    -0.07
    POSITIVE LOGITS
    Ӡ
    0.07
     Odd
    0.07
    东方
    0.07
    ﺘ
    0.07
    מסך
    0.07
    uchi
    0.06
    �
    0.06
     valleys
    0.06
     וה
    0.06
    这座
    0.06
    Act Density 0.060%

    No Known Activations