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

    Neuronpedia

    INDEX
    Explanations

    PT

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     plight
    -0.07
    kání
    -0.06
     Oscars
    -0.06
     Rad
    -0.06
     카
    -0.06
     року
    -0.06
    ็นอ
    -0.06
    �
    -0.06
    =&
    -0.06
     کام
    -0.06
    POSITIVE LOGITS
     experimented
    0.06
    perimental
    0.06
     سلام
    0.06
     cleanup
    0.06
     Shepard
    0.06
     listen
    0.06
     slept
    0.06
     Early
    0.06
     Officers
    0.06
     Massachusetts
    0.06
    Act Density 0.005%

    No Known Activations