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

    Neuronpedia

    INDEX
    Explanations

    sequence, continuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     follows
    -2.00
     follow
    -1.74
    follows
    -1.59
    follow
    -1.52
    Follow
    -1.51
     Follow
    -1.37
     FOLLOW
    -1.30
     volgt
    -1.30
     Follows
    -1.24
     folgt
    -1.22
    POSITIVE LOGITS
    withIdentifier
    0.80
     the
    0.70
    ories
    0.64
     intptr
    0.59
    passing
    0.59
    TORE
    0.59
    bewerken
    0.59
    ANCE
    0.56
    got
    0.55
    󠁢
    0.55
    Act Density 0.024%

    No Known Activations