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

    Neuronpedia

    INDEX
    Explanations

    condemned to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Potts
    0.40
     confronti
    0.35
    🛵
    0.34
     strtok
    0.34
     ()
    0.32
    bery
    0.32
    🚿
    0.32
    Holstein
    0.32
     ไหร่
    0.32
     마무리
    0.32
    POSITIVE LOGITS
     blandit
    0.40
    OGRAF
    0.40
     par
    0.39
     nt
    0.39
    ılar
    0.38
     Especific
    0.38
     Об
    0.37
    смо
    0.37
    KT
    0.37
     recogn
    0.36
    Act Density 0.001%

    No Known Activations