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

    Neuronpedia

    INDEX
    Explanations

    job

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     batt
    -0.29
    ertas
    -0.28
    å½ĵãģ¦
    -0.27
    ìħĭ
    -0.26
     Missile
    -0.26
    aint
    -0.25
     ngũ
    -0.25
    azine
    -0.25
    grave
    -0.24
    Updating
    -0.24
    POSITIVE LOGITS
     Nak
    0.30
    dbo
    0.28
    tep
    0.28
     Kawasaki
    0.26
    ymous
    0.26
    ASTE
    0.25
    çĥĺå¹²
    0.24
    period
    0.24
    以èĩ³äºİ
    0.24
    amus
    0.24
    Act Density 0.006%

    No Known Activations