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

    Neuronpedia

    INDEX
    Explanations

    youalready installed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Funds
    0.52
    ന്മ
    0.49
    Size
    0.49
     ছাউ
    0.48
     urt
    0.47
    curso
    0.47
     Secrets
    0.47
     Modem
    0.47
     Técnico
    0.47
    Money
    0.46
    POSITIVE LOGITS
     জনসং
    0.48
    tilde
    0.46
     ህ
    0.46
    >);
    0.46
     prenant
    0.46
    ઙ
    0.46
    剥
    0.45
    воря
    0.44
     squeezed
    0.43
     clog
    0.43
    Act Density 0.000%

    No Known Activations