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

    Neuronpedia

    INDEX
    Explanations

    look at, think about

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    malign
    0.40
    lieu
    0.36
     malignancy
    0.34
     माली
    0.34
    reactive
    0.33
    molecule
    0.33
    mdi
    0.33
    frying
    0.33
    teman
    0.32
    discharge
    0.32
    POSITIVE LOGITS
     meriye
    0.34
    М
    0.34
    JZ
    0.33
    ്രാ
    0.32
     scriptures
    0.31
    orsunuz
    0.31
    Rajas
    0.31
     சமீப
    0.31
     kurie
    0.30
     பகுதியில்
    0.30
    Act Density 0.000%

    No Known Activations