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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Built
    -0.07
    ίσω
    -0.06
     po
    -0.06
     nakne
    -0.06
    ITHUB
    -0.06
    \Desktop
    -0.06
    Particle
    -0.06
    .UN
    -0.06
    ypse
    -0.06
    	graph
    -0.06
    POSITIVE LOGITS
    iteur
    0.06
    odie
    0.06
    employed
    0.06
    :t
    0.06
    tie
    0.06
    uffer
    0.06
     dedicated
    0.06
    连
    0.06
    .constant
    0.05
    arity
    0.05
    Act Density 0.033%

    No Known Activations