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

    Neuronpedia

    INDEX
    Explanations

    website

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ARAM
    -0.06
    xyz
    -0.06
     HL
    -0.06
    otoxic
    -0.06
     marginalized
    -0.06
     BIN
    -0.06
     месяцев
    -0.06
    $self
    -0.06
     वन
    -0.06
     thinly
    -0.06
    POSITIVE LOGITS
    ومی
    0.07
    -ves
    0.06
    .heading
    0.06
    Kir
    0.06
     Destructor
    0.06
     popping
    0.06
     переб
    0.06
     Packs
    0.06
    <Animator
    0.06
    	IL
    0.06
    Act Density 0.017%

    No Known Activations