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

    Neuronpedia

    INDEX
    Explanations

    -align

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     swept
    -0.07
     rumors
    -0.07
     TEX
    -0.07
     Με
    -0.07
    aned
    -0.06
     Consult
    -0.06
     Reception
    -0.06
     KEEP
    -0.06
     rumor
    -0.06
    NOWLED
    -0.06
    POSITIVE LOGITS
    ेल
    0.07
     Donovan
    0.06
     appe
    0.06
    .''
    0.06
     現
    0.06
    �
    0.06
    ivet
    0.06
    quals
    0.06
    ẩy
    0.06
    ीवन
    0.06
    Act Density 0.001%

    No Known Activations