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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    увався
    -0.07
    .Documents
    -0.07
     countert
    -0.07
    aside
    -0.07
    يف
    -0.06
    multiply
    -0.06
    observe
    -0.06
    -pointer
    -0.06
     rm
    -0.06
     dictate
    -0.06
    POSITIVE LOGITS
    RUN
    0.07
    ISTORY
    0.07
     Bulk
    0.07
    ekk
    0.07
    Caught
    0.06
    �
    0.06
    kb
    0.06
    groupid
    0.06
     маст
    0.06
    شان
    0.06
    Act Density 0.005%

    No Known Activations