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

    Neuronpedia

    INDEX
    Explanations

    Internal thoughts/dialogue

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scholar
    -0.07
    Fashion
    -0.07
    ують
    -0.06
    iterated
    -0.06
    Gs
    -0.06
    asil
    -0.06
    -0.06
    	sub
    -0.06
    Extended
    -0.06
     عبد
    -0.06
    POSITIVE LOGITS
     keyCode
    0.06
     απο
    0.06
     Kurulu
    0.06
     Daytona
    0.06
    textures
    0.06
     หาก
    0.06
     sympathy
    0.06
    ngine
    0.06
     kvinna
    0.06
     gunshot
    0.06
    Act Density 0.064%

    No Known Activations