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

    Neuronpedia

    INDEX
    Explanations

    Liquid spills

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    *e
    -0.07
    madığı
    -0.07
     preceded
    -0.06
    roups
    -0.06
    ував
    -0.06
     Credentials
    -0.06
    tat
    -0.06
     state
    -0.06
     쪽
    -0.06
    resents
    -0.06
    POSITIVE LOGITS
     spills
    0.14
     spill
    0.13
     spilled
    0.12
    _phy
    0.07
    ¸
    0.07
    -public
    0.07
    .SpringApplication
    0.07
     klar
    0.07
    ชน
    0.06
     Pratt
    0.06
    Act Density 0.002%

    No Known Activations