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

    Neuronpedia

    INDEX
    Explanations

    often depicted, adapt specific, recent years, rare weather

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    цька
    0.53
     پتہ
    0.52
     коюм
    0.51
     Ага
    0.50
     সেকেন্ড
    0.49
     Затем
    0.48
    ূর
    0.48
     बीसीसीआई
    0.48
    らの
    0.48
     बालकनियां
    0.48
    POSITIVE LOGITS
    k
    0.63
    o
    0.61
     a
    0.60
    a
    0.55
    u
    0.54
    c
    0.51
    w
    0.50
    e
    0.49
     m
    0.47
    (-
    0.46
    Act Density 0.001%

    No Known Activations