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

    Neuronpedia

    INDEX
    Explanations

    count distinct elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Beverly
    0.46
     Dot
    0.46
     grace
    0.45
    ̏
    0.44
    밥
    0.44
     Grade
    0.43
     Parish
    0.42
     recount
    0.42
     name
    0.42
     dot
    0.42
    POSITIVE LOGITS
     பாதுகாக்க
    0.55
    ដែលអាច
    0.52
    holomorphic
    0.47
    deterministic
    0.46
    ر
    0.46
    fins
    0.45
    ovali
    0.44
    poque
    0.44
    pe
    0.43
    er
    0.42
    Act Density 0.001%

    No Known Activations