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

    Neuronpedia

    INDEX
    Explanations

    column vector

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    across
    0.47
     studded
    0.41
    hiti
    0.40
    boarding
    0.39
    asting
    0.38
    Width
    0.38
     across
    0.38
    bord
    0.38
    proud
    0.38
    Layer
    0.37
    POSITIVE LOGITS
     columna
    0.45
     bienvenida
    0.44
     phối
    0.42
     kolom
    0.40
     rétr
    0.40
     bào
    0.39
     eigenvector
    0.39
     cara
    0.39
     neder
    0.38
     column
    0.38
    Act Density 0.003%

    No Known Activations