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

    Neuronpedia

    INDEX
    Explanations

    Strong or convincing arguments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.74
     vectorielles
    -0.70
    CodeAttribute
    -0.67
     lenker
    -0.67
     credible
    -0.67
    AndEndTag
    -0.67
     pinulongan
    -0.66
    Aiheesta
    -0.66
     believable
    -0.63
     للمعارف
    -0.63
    POSITIVE LOGITS
    er
    0.67
    ly
    0.53
    hassee
    0.49
    cut
    0.48
    ooplankton
    0.47
    w
    0.47
    ER
    0.46
    Beam
    0.46
    ges
    0.45
    cur
    0.45
    Act Density 0.090%

    No Known Activations