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

    Neuronpedia

    INDEX
    Explanations

    Here's a quick

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ocèle
    0.39
     Ethyl
    0.35
    粒
    0.35
     sidew
    0.34
     precisam
    0.34
    ydney
    0.34
    があるので
    0.33
    <0x8B>
    0.33
    uttle
    0.33
     Fedora
    0.33
    POSITIVE LOGITS
     हिम्मत
    0.40
    nows
    0.39
     Ch
    0.39
    fins
    0.38
    াপে
    0.37
     polit
    0.37
     ch
    0.37
    வன
    0.36
     sincerely
    0.36
    ichtlich
    0.36
    Act Density 0.000%

    No Known Activations