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

    Neuronpedia

    INDEX
    Explanations

    Test, breeding, grief

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ன்மையான
    0.39
    Toxic
    0.39
     équipée
    0.39
    沄
    0.38
    Titanic
    0.38
    чні
    0.38
    Retention
    0.38
    Biome
    0.37
    Conditional
    0.37
    триму
    0.36
    POSITIVE LOGITS
     डॉन
    0.34
    攏
    0.33
    पछि
    0.32
    "><
    0.32
    etchup
    0.32
    эл
    0.31
     deslig
    0.31
     dijete
    0.30
     শাসন
    0.30
    ᱥ
    0.30
    Act Density 0.000%

    No Known Activations