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

    Neuronpedia

    INDEX
    Explanations

    depths of physical structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pubblici
    0.41
     депута
    0.40
    зиден
    0.39
     Politik
    0.39
     politischen
    0.38
     notizia
    0.37
     pubblico
    0.37
     cittadini
    0.37
     kebijakan
    0.37
     sanciones
    0.37
    POSITIVE LOGITS
    components
    0.38
     cylindrical
    0.37
     components
    0.37
    water
    0.37
    axis
    0.37
    profile
    0.37
     curved
    0.37
    line
    0.36
    structure
    0.36
     screws
    0.36
    Act Density 0.000%

    No Known Activations