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

    Neuronpedia

    INDEX
    Explanations

    confidential JSON URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᡤ
    0.42
    Ahh
    0.40
     канали
    0.40
     Ahu
    0.39
    Viv
    0.37
     Mapa
    0.36
     अह
    0.36
    apayati
    0.35
    蓼
    0.35
     Ahm
    0.35
    POSITIVE LOGITS
     flex
    0.36
     tough
    0.34
     suit
    0.34
     Hastings
    0.34
    汁
    0.33
    fer
    0.33
    juk
    0.33
     ken
    0.33
    ibo
    0.33
    tough
    0.33
    Act Density 0.013%

    No Known Activations