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

    Neuronpedia

    INDEX
    Explanations

    own

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fear
    -0.06
    더
    -0.06
    ールド
    -0.06
    dek
    -0.06
     Fedora
    -0.06
     práva
    -0.06
     assume
    -0.06
    Relationship
    -0.06
    Ideal
    -0.06
    agi
    -0.06
    POSITIVE LOGITS
     own
    0.07
     Own
    0.07
    .setting
    0.07
    .HeaderText
    0.06
    feedback
    0.06
    /thumb
    0.06
     Furn
    0.06
    _own
    0.06
     присутств
    0.06
    bst
    0.06
    Act Density 0.016%

    No Known Activations