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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -next
    -0.09
    .next
    -0.08
     previous
    -0.08
    .previous
    -0.08
    �
    -0.07
     બોલ
    -0.07
    _next
    -0.07
    חה
    -0.07
    existing
    -0.07
     married
    -0.07
    POSITIVE LOGITS
     Coup
    0.09
     __________________
    0.09
     Snap
    0.09
     __________________________________
    0.09
     Telecommunications
    0.08
     Diret
    0.08
    iteerd
    0.08
     Resol
    0.08
     Directors
    0.08
     naap
    0.08
    Act Density 0.005%

    No Known Activations