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

    Neuronpedia

    INDEX
    Explanations

    need to define rules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    配置
    0.44
    ٠
    0.44
    robe
    0.40
    λει
    0.40
    勾
    0.40
     அல்
    0.39
    州
    0.39
    gov
    0.37
     અવ
    0.37
    随着
    0.37
    POSITIVE LOGITS
     Espan
    0.41
     Dent
    0.38
     Clements
    0.36
     continu
    0.36
     scarlet
    0.36
    𒅴
    0.35
     Greg
    0.35
     Repeat
    0.34
     سمجھ
    0.34
     Sandoval
    0.34
    Act Density 0.000%

    No Known Activations