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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     bangunan
    0.73
    ید
    0.64
    تا
    0.63
    HOW
    0.61
     meningkat
    0.61
    Utilities
    0.61
     атмос
    0.61
    progressbar
    0.60
    сист
    0.59
     बढ़ता
    0.59
    POSITIVE LOGITS
    ો
    0.68
     prohibited
    0.68
     vollständig
    0.65
     chloride
    0.64
     sculpted
    0.64
     bị
    0.63
     /=
    0.63
     bypassed
    0.62
    א
    0.62
     perpetrators
    0.61
    Act Density 0.000%

    No Known Activations