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

    Neuronpedia

    INDEX
    Explanations

    full

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    izienz
    -0.09
     Kortom
    -0.08
    Ос
    -0.08
     Strict
    -0.08
     строго
    -0.08
    Datos
    -0.08
     magiging
    -0.08
     கருத்த
    -0.07
    atasets
    -0.07
     исследований
    -0.07
    POSITIVE LOGITS
     hardwood
    0.08
    -use
    0.07
     symbole
    0.07
     miniature
    0.07
     vår
    0.07
    -en
    0.07
     imprim
    0.07
     cartoon
    0.07
     begin
    0.07
     Billy
    0.07
    Act Density 0.274%

    No Known Activations