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

    Neuronpedia

    INDEX
    Explanations

    false

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     upkeep
    -0.07
     terrain
    -0.06
     Install
    -0.06
     unveiled
    -0.06
     beer
    -0.06
    .Elements
    -0.05
    ━
    -0.05
     découvrir
    -0.05
     Truman
    -0.05
    (ok
    -0.05
    POSITIVE LOGITS
    ुच
    0.07
     unify
    0.07
    .TextBox
    0.07
     falsely
    0.07
    lán
    0.07
    τας
    0.07
    ��
    0.07
     percentages
    0.07
     FormsModule
    0.07
    UTES
    0.07
    Act Density 0.009%

    No Known Activations