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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ࡢ
    -0.07
     Planned
    -0.07
    הולך
    -0.07
    -output
    -0.07
    둿
    -0.07
    (set
    -0.06
    高血压
    -0.06
    ︖
    -0.06
     Совет
    -0.06
    콧
    -0.06
    POSITIVE LOGITS
     strstr
    0.08
    Sİ
    0.07
     scram
    0.07
     Wife
    0.07
     astro
    0.07
    rice
    0.07
     summer
    0.07
     superhero
    0.07
    حرم
    0.07
     supplying
    0.07
    Act Density 0.044%

    No Known Activations