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

    Neuronpedia

    INDEX
    Explanations

    code/technical snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (isset
    -0.07
    enity
    -0.06
     raj
    -0.06
    ですね
    -0.06
    zí
    -0.06
     Ö
    -0.06
    @section
    -0.06
    'A
    -0.06
    checkbox
    -0.06
     który
    -0.06
    POSITIVE LOGITS
     replic
    0.07
     comedic
    0.07
     translator
    0.07
     verschied
    0.07
    mov
    0.06
    にして
    0.06
    comm
    0.06
     Missile
    0.06
    vas
    0.06
    assage
    0.06
    Act Density 0.000%

    No Known Activations