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

    Neuronpedia

    INDEX
    Explanations

    vier

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     directional
    -0.09
     jos
    -0.08
     equival
    -0.08
     appreciates
    -0.08
     جهت
    -0.08
    ieważ
    -0.08
     faithful
    -0.07
     Appreciate
    -0.07
     curricular
    -0.07
     appreciated
    -0.07
    POSITIVE LOGITS
     piracy
    0.08
    态
    0.08
    play
    0.08
     ойын
    0.08
     pir
    0.08
     Organisation
    0.08
    Organisation
    0.08
     rotten
    0.08
    Pd
    0.08
     playoff
    0.08
    Act Density 0.002%

    No Known Activations