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

    Neuronpedia

    INDEX
    Explanations

    Post

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bras
    -0.07
     kvm
    -0.06
    лия
    -0.06
    IELDS
    -0.06
     سلام
    -0.06
    итуа
    -0.06
    _planes
    -0.06
    THON
    -0.06
    (Unit
    -0.06
    =in
    -0.06
    POSITIVE LOGITS
     Post
    0.10
    0.07
    xff
    0.07
    0.07
     echt
    0.07
     والتي
    0.07
    .compare
    0.07
     Sheridan
    0.06
    .Direction
    0.06
    ού
    0.06
    Act Density 0.004%

    No Known Activations