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

    Neuronpedia

    INDEX
    Explanations

    assisting users

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    raig
    -0.09
    omb
    -0.09
     McCorm
    -0.09
    orn
    -0.08
    olar
    -0.08
     constit
    -0.08
     rem
    -0.08
    t
    -0.08
    vt
    -0.08
     Goodman
    -0.08
    POSITIVE LOGITS
     like
    0.21
     nhÆ°
    0.15
     zoals
    0.13
     seperti
    0.12
     Like
    0.12
    krv
    0.11
    åĥı
    0.11
     LIKE
    0.11
    Like
    0.10
     como
    0.10
    Act Density 0.029%

    No Known Activations