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

    Neuronpedia

    INDEX
    Explanations

    product features and design

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     APP
    -0.07
     �
    -0.07
     виснов
    -0.06
     Prahy
    -0.06
     RAND
    -0.06
     pás
    -0.06
    	strcat
    -0.06
    quiv
    -0.06
     наслед
    -0.06
    βάλ
    -0.06
    POSITIVE LOGITS
     được
    0.07
    Purple
    0.07
    }")
↵
    0.07
    ])
↵
    0.06
    ійс
    0.06
    .Tasks
    0.06
    	Image
    0.06
    Door
    0.06
    elage
    0.06
     chase
    0.06
    Act Density 0.110%

    No Known Activations