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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     testing
    -0.08
    esium
    -0.07
    PP
    -0.07
    PageIndex
    -0.07
    AM
    -0.07
    ENTIAL
    -0.07
    Signing
    -0.07
     Ta
    -0.07
     INF
    -0.07
    ци
    -0.07
    POSITIVE LOGITS
    龌
    0.08
    蝴
    0.07
     Ambient
    0.07
     hilar
    0.07
     lesbian
    0.06
    (contact
    0.06
    kür
    0.06
     fluores
    0.06
     رس
    0.06
     controvers
    0.06
    Act Density 0.091%

    No Known Activations