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

    Neuronpedia

    INDEX
    Explanations

    Prompt formatting rules

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    35
    -0.08
     wander
    -0.08
     walkthrough
    -0.07
     consult
    -0.07
     migr
    -0.07
    acam
    -0.07
     stroll
    -0.07
     Zusch
    -0.07
    Cannot
    -0.07
     skal
    -0.07
    POSITIVE LOGITS
     necesariamente
    0.09
     heure
    0.09
    уы
    0.09
     necessariamente
    0.08
     hoeft
    0.08
     particulière
    0.08
     cerve
    0.08
     gọi
    0.08
     necessarily
    0.08
     hoef
    0.08
    Act Density 0.003%

    No Known Activations