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

    Neuronpedia

    INDEX
    Explanations

    be

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Shares
    -0.09
    Understanding
    -0.09
    Authorities
    -0.08
    Diagnosis
    -0.08
    Allocate
    -0.08
    Negoti
    -0.08
    Ratings
    -0.08
    Symbol
    -0.08
    Desired
    -0.08
    Distribution
    -0.08
    POSITIVE LOGITS
     Gerade
    0.11
     axis
    0.10
     například
    0.09
     transversal
    0.09
     axes
    0.09
     eixo
    0.09
     plane
    0.09
     näiteks
    0.09
     transverse
    0.09
     Plane
    0.09
    Act Density 0.008%

    No Known Activations