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

    Neuronpedia

    INDEX
    Explanations

    cause, followed by asymmetry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     veil
    0.50
     تحت
    0.39
     curtain
    0.38
     dign
    0.38
     поверхность
    0.38
     এরই
    0.38
    Proveedor
    0.37
     povr
    0.37
    ിലാണ്
    0.37
     மேற்பர
    0.37
    POSITIVE LOGITS
    поль
    0.45
    eye
    0.42
    handed
    0.39
    lof
    0.37
     Lapp
    0.36
     Lapse
    0.36
    聝
    0.36
    hor
    0.36
     Steep
    0.35
    wit
    0.35
    Act Density 0.000%

    No Known Activations