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

    Neuronpedia

    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ry
    -0.07
    /card
    -0.06
    azzi
    -0.06
    Wa
    -0.06
    877
    -0.06
    -direct
    -0.06
     tipped
    -0.06
    enco
    -0.06
    -neutral
    -0.06
     Thor
    -0.06
    POSITIVE LOGITS
     —
    0.07
    Recommended
    0.07
    Relationship
    0.06
     CLR
    0.06
    portion
    0.06
    법
    0.06
     transitioning
    0.06
     loans
    0.06
    WRITE
    0.06
     Alternative
    0.06
    Act Density 0.022%

    No Known Activations