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

    Neuronpedia

    INDEX
    Explanations

    code overload/methods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     calculus
    -0.07
    Mon
    -0.07
    	Draw
    -0.06
    accel
    -0.06
     dusty
    -0.06
     Henri
    -0.06
     Oral
    -0.06
    Fluid
    -0.06
    _cs
    -0.06
     sqrt
    -0.06
    POSITIVE LOGITS
     teammate
    0.07
     septembre
    0.07
    strings
    0.07
     financially
    0.06
    acak
    0.06
     households
    0.06
    /octet
    0.06
    WARDED
    0.06
     тощо
    0.06
     Snackbar
    0.06
    Act Density 0.042%

    No Known Activations