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

    Neuronpedia

    INDEX
    Explanations

    fields, recordings, powder

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vaisseaux
    0.56
     rutrum
    0.52
    드시
    0.52
     ರೀತಿ
    0.51
     calendriers
    0.50
     разнообраз
    0.49
     drawed
    0.49
     RADIOACTIVE
    0.49
    োপুরি
    0.49
     ভাইরাস
    0.49
    POSITIVE LOGITS
    ter
    0.58
     O
    0.54
     I
    0.53
     R
    0.52
    ken
    0.50
    ström
    0.49
     This
    0.48
    ie
    0.48
    low
    0.48
     H
    0.47
    Act Density 0.000%

    No Known Activations