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

    Neuronpedia

    INDEX
    Explanations

    /

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
            
↵
    -0.07
    бач
    -0.07
     invade
    -0.07
     recorder
    -0.07
    Executive
    -0.06
    .Method
    -0.06
     spectacle
    -0.06
     Attend
    -0.06
     page
    -0.06
     dri
    -0.06
    POSITIVE LOGITS
     δυνα
    0.08
     anchored
    0.07
    .top
    0.07
    око
    0.07
    Ratio
    0.06
    _%
    0.06
    �
    0.06
     množství
    0.05
     kür
    0.05
    RED
    0.05
    Act Density 0.007%

    No Known Activations