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

    Neuronpedia

    INDEX
    Explanations

    have or for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    е
    0.52
    ﻓ
    0.49
    я
    0.48
    אר
    0.47
    Hosting
    0.46
    то
    0.46
    в
    0.45
    <0xA3>
    0.45
    व्ह
    0.44
    ının
    0.44
    POSITIVE LOGITS
     Zoological
    0.49
     zaradi
    0.45
     gratefully
    0.45
     zape
    0.44
     blij
    0.44
     backlight
    0.43
     puri
    0.43
     Mikolai
    0.43
     apoptotic
    0.42
    eneuve
    0.42
    Act Density 0.014%

    No Known Activations