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

    Neuronpedia

    INDEX
    Explanations

    before or after

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Gál
    0.41
     herramient
    0.41
     García
    0.41
     حسین
    0.41
     juxtaposition
    0.40
    𒁀
    0.40
     generaciones
    0.39
     Goodwin
    0.39
     getConfig
    0.39
    adocia
    0.39
    POSITIVE LOGITS
    gies
    0.39
    ties
    0.39
     TVs
    0.39
    TV
    0.36
    /
    0.35
    途
    0.34
    PM
    0.33
     sourced
    0.33
     engines
    0.33
     BEFORE
    0.33
    Act Density 0.003%

    No Known Activations