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

    Neuronpedia

    INDEX
    Explanations

    For

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     handler
    -0.07
    organizations
    -0.06
    ента
    -0.06
    iedade
    -0.06
     Experts
    -0.06
    ें
    -0.06
    (URL
    -0.06
    "./
    -0.06
     averages
    -0.06
    哭
    -0.06
    POSITIVE LOGITS
    irket
    0.06
    .son
    0.06
     Ro
    0.06
     peasant
    0.06
    illusion
    0.06
    .when
    0.06
    '));
↵
    0.06
    CTSTR
    0.06
     жит
    0.06
     eşit
    0.06
    Act Density 0.011%

    No Known Activations