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

    Neuronpedia

    INDEX
    Explanations

    color and unicode settings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    輿
    0.38
    мно
    0.38
    υχ
    0.37
    че
    0.36
     astr
    0.35
    られている
    0.35
     дослід
    0.35
    पीरियंस
    0.35
     осигура
    0.35
    苡
    0.34
    POSITIVE LOGITS
     color
    0.51
     colour
    0.49
    color
    0.46
     kleur
    0.46
    unicode
    0.46
    setColor
    0.44
    getColor
    0.42
    utf
    0.42
     colore
    0.42
     berwarna
    0.42
    Act Density 0.000%

    No Known Activations