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

    Neuronpedia

    INDEX
    Explanations

    common topics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     remarked
    -0.08
     marked
    -0.08
    .F
    -0.07
     crisp
    -0.07
     partir
    -0.07
    �்
    -0.07
    .translate
    -0.07
    .tight
    -0.07
     शूट
    -0.07
     contextual
    -0.07
    POSITIVE LOGITS
     duniya
    0.12
     العالم
    0.10
     בעולם
    0.10
     الدنيا
    0.10
     imaginable
    0.10
     دنیا
    0.10
     düny
    0.10
     conceivable
    0.10
     संसार
    0.09
     পৃথিব
    0.09
    Act Density 0.048%

    No Known Activations