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

    Neuronpedia

    INDEX
    Explanations

    GGUF

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sanitary
    0.40
    hips
    0.40
    Partners
    0.39
     !!
    0.38
    knak
    0.38
     สาว
    0.38
     kaha
    0.37
     Concept
    0.37
     sahab
    0.36
     kiu
    0.36
    POSITIVE LOGITS
     Wolfgang
    0.42
     பய
    0.40
    azin
    0.36
    adka
    0.36
    FERRED
    0.35
     ROWS
    0.35
     inhomogeneous
    0.34
    ardin
    0.34
     elk
    0.34
    ódulo
    0.34
    Act Density 0.001%

    No Known Activations