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

    Neuronpedia

    INDEX
    Explanations

    exploring configurations and official responses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ман
    0.39
     जोड
    0.37
    спеди
    0.37
    轄
    0.37
    ഴിലാ
    0.36
    льше
    0.36
     modalidad
    0.35
     Modes
    0.35
    椥
    0.35
    চনার
    0.35
    POSITIVE LOGITS
    rd
    0.42
     विरा
    0.41
     Aid
    0.39
    Aid
    0.39
    fails
    0.39
    Vir
    0.39
    Tak
    0.39
    Fail
    0.38
    fail
    0.38
    Fps
    0.38
    Act Density 0.000%

    No Known Activations