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

    Neuronpedia

    INDEX
    Explanations

    residences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    鸯
    -0.27
     Armstrong
    -0.26
    CEED
    -0.25
    omit
    -0.25
    åĵªå®¶
    -0.25
    åıŁ
    -0.24
    abilit
    -0.23
    глаÑģ
    -0.23
    éĥ¨ä»½
    -0.23
    itim
    -0.23
    POSITIVE LOGITS
     brink
    0.27
    決
    0.25
    land
    0.25
    ToFront
    0.25
     AppModule
    0.24
    ALLEL
    0.24
     thresholds
    0.24
     threshold
    0.24
    idia
    0.24
    .catalog
    0.23
    Act Density 0.036%

    No Known Activations