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

    Neuronpedia

    INDEX
    Explanations

    charm

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     과
    -0.07
     swift
    -0.07
    ificacion
    -0.07
     Rac
    -0.07
     gluc
    -0.06
    National
    -0.06
    rowable
    -0.06
     fortified
    -0.06
    �
    -0.06
     외국
    -0.06
    POSITIVE LOGITS
     charm
    0.13
     charming
    0.11
    .CH
    0.09
     charms
    0.09
     Charm
    0.09
    charm
    0.08
    	AM
    0.08
    CHAR
    0.07
    /MM
    0.07
     charter
    0.07
    Act Density 0.005%

    No Known Activations