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

    Neuronpedia

    INDEX
    Explanations

    TEXT

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ее
    -0.07
     chest
    -0.07
    cest
    -0.07
    温
    -0.06
     spouse
    -0.06
     simulation
    -0.06
     sidelines
    -0.06
     connects
    -0.06
    est
    -0.06
     mode
    -0.06
    POSITIVE LOGITS
     mekt
    0.07
     CRA
    0.06
    ίτ
    0.06
     PS
    0.06
    装置
    0.06
    ¦
    0.06
    belie
    0.06
    átor
    0.06
     LS
    0.06
     fetisch
    0.06
    Act Density 0.000%

    No Known Activations