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

    Neuronpedia

    INDEX
    Explanations

    frontend JavaScript close

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    consolid
    0.43
     සහ
    0.40
    unately
    0.40
    yielding
    0.39
    ﭥ
    0.39
    机
    0.38
    α
    0.38
    roit
    0.38
    asshi
    0.38
    account
    0.37
    POSITIVE LOGITS
     Polsce
    0.44
     fero
    0.43
     individuais
    0.43
     š
    0.43
     brazos
    0.43
     [/
    0.43
     estern
    0.42
     Limited
    0.42
     No
    0.41
     dizer
    0.41
    Act Density 0.001%

    No Known Activations