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

    Neuronpedia

    INDEX
    Explanations

    quotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     malls
    -0.07
     IBM
    -0.07
    Li
    -0.06
    [js
    -0.06
     mujer
    -0.06
    แค
    -0.06
    SUMER
    -0.06
     SATA
    -0.06
    eker
    -0.06
    .EXP
    -0.06
    POSITIVE LOGITS
    uddenly
    0.07
    rays
    0.07
    ζει
    0.07
     。↵
    0.06
     відпов
    0.06
    shutdown
    0.06
    τους
    0.06
    Driver
    0.06
     }
↵
↵
↵
    0.06
    λα
    0.06
    Act Density 0.002%

    No Known Activations