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
    “We
    -0.08
    “There
    -0.07
    refix
    -0.07
    :|
    -0.07
     Zwe
    -0.07
    ха
    -0.07
    $user
    -0.07
    userid
    -0.06
    "We
    -0.06
    CGFloat
    -0.06
    POSITIVE LOGITS
     Scala
    0.07
     envelop
    0.06
    -java
    0.06
    canf
    0.06
    \Entities
    0.06
     пож
    0.06
     sanitizer
    0.06
    plet
    0.06
     threadIdx
    0.05
     अज
    0.05
    Act Density 0.004%

    No Known Activations