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

    Neuronpedia

    INDEX
    Explanations

    Theories and studies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     đáng
    -0.07
     vzděl
    -0.06
     facility
    -0.06
     Egypt
    -0.06
    classify
    -0.06
    θή
    -0.06
    cost
    -0.06
     hike
    -0.06
     gadgets
    -0.06
     disproportionately
    -0.06
    POSITIVE LOGITS
    ید
    0.07
    _toolbar
    0.07
    .checkBox
    0.07
    ох
    0.07
     останов
    0.06
    _rs
    0.06
     jewels
    0.06
     сигн
    0.06
    .SetToolTip
    0.06
     тех
    0.06
    Act Density 0.047%

    No Known Activations