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

    Neuronpedia

    INDEX
    Explanations

    "This is" structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     monotonically
    0.52
     constraint
    0.49
     perturbation
    0.47
     subsequ
    0.46
     penalized
    0.46
     perturb
    0.45
     deformation
    0.44
     spacetime
    0.44
     fetus
    0.43
     extraneous
    0.43
    POSITIVE LOGITS
     ■
    0.64
     fi
    0.55
    ■
    0.54
     •
    0.54
    ➊
    0.51
     PHOTO
    0.49
     tions
    0.48
     FEBRUARY
    0.48
    fi
    0.46
    fl
    0.46
    Act Density 0.001%

    No Known Activations