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

    Neuronpedia

    INDEX
    Explanations

    concern

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sf
    -0.07
    dr
    -0.07
    .Authentication
    -0.07
    tat
    -0.07
    Lit
    -0.07
    Το
    -0.07
     Tyler
    -0.07
     lith
    -0.07
     thyroid
    -0.07
     melted
    -0.07
    POSITIVE LOGITS
     concern
    0.13
     concerns
    0.13
     concerned
    0.12
     Concern
    0.09
     concerning
    0.09
    cern
    0.08
     Anchor
    0.07
    ammu
    0.07
     conducts
    0.07
     بالق
    0.07
    Act Density 0.016%

    No Known Activations