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

    Neuronpedia

    INDEX
    Explanations

    investigate and declare

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    かなり
    0.41
     Boga
    0.38
    Laser
    0.37
     pade
    0.37
    elegant
    0.36
     radial
    0.36
    ोब
    0.35
    fade
    0.34
     Candidate
    0.34
    radial
    0.34
    POSITIVE LOGITS
     inquiry
    0.42
     investigate
    0.41
     enquiry
    0.41
     वेरी
    0.39
     unexplained
    0.39
     dichiar
    0.39
    PolicyQuery
    0.39
     安心
    0.39
    ureau
    0.38
     declaración
    0.38
    Act Density 0.003%

    No Known Activations