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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Through
    -0.08
     в
    -0.07
    عبر
    -0.07
     spinner
    -0.07
    .dw
    -0.07
    (run
    -0.07
    ##
    -0.07
    .nz
    -0.07
     spear
    -0.07
     twins
    -0.07
    POSITIVE LOGITS
     hesitation
    0.07
    뤂
    0.07
    ??
    0.06
     hormones
    0.06
     coherence
    0.06
    ）
    0.06
    limit
    0.06
     kości
    0.06
    /firebase
    0.06
    PHY
    0.06
    Act Density 0.192%

    No Known Activations