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

    Neuronpedia

    INDEX
    Explanations

    answering questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ylland
    -0.06
    anical
    -0.06
    	align
    -0.06
    ورش
    -0.06
    }).
    -0.06
    .Writer
    -0.06
     +**************
    -0.06
     notification
    -0.06
     finden
    -0.06
    arger
    -0.05
    POSITIVE LOGITS
    ookie
    0.07
     convened
    0.07
     unhappy
    0.06
    (false
    0.06
     النو
    0.06
    _twitter
    0.06
    \ActiveForm
    0.06
     České
    0.06
     unwrap
    0.06
    (qu
    0.06
    Act Density 0.068%

    No Known Activations