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

    Neuronpedia

    INDEX
    Explanations

    not working

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     REQUI
    0.49
     necesitar
    0.47
     Requires
    0.47
     perlu
    0.46
    Requires
    0.46
     cần
    0.46
     besoin
    0.45
     reqParams
    0.44
     bisogno
    0.44
     requires
    0.43
    POSITIVE LOGITS
     properly
    0.85
     correctly
    0.75
     cooperate
    0.73
     reliably
    0.71
    proper
    0.70
     corretamente
    0.67
     successfully
    0.66
     correctement
    0.66
     correctamente
    0.65
     succesfully
    0.65
    Act Density 0.020%

    No Known Activations