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

    Neuronpedia

    INDEX
    Explanations

    version: and following metadata

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ul
    0.38
    Addition
    0.38
     fieldValue
    0.38
    ऐ
    0.38
    Ki
    0.38
    Roses
    0.37
    Vas
    0.37
    EST
    0.36
    Alban
    0.36
    Mgr
    0.36
    POSITIVE LOGITS
     programm
    0.40
     devol
    0.38
     mecan
    0.37
     Times
    0.36
     Planck
    0.36
     chale
    0.36
     objetivos
    0.36
    લાઈ
    0.35
     Physically
    0.35
     onwards
    0.35
    Act Density 0.026%

    No Known Activations