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

    Neuronpedia

    INDEX
    Explanations

    JavaScript function definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    umbent
    0.69
    meas
    0.65
     dissemination
    0.65
    map
    0.63
    compatible
    0.61
    she
    0.60
    posterous
    0.59
    entery
    0.59
     map
    0.59
     aspires
    0.59
    POSITIVE LOGITS
     არს
    0.91
     mág
    0.85
    েক্টর
    0.85
    že
    0.84
    か月
    0.84
     や
    0.84
     alcuni
    0.83
    ೀಲ
    0.82
    біль
    0.82
     लहर
    0.82
    Act Density 0.001%

    No Known Activations