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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    JsonIgnore
    -0.07
    ätze
    -0.07
     discouraged
    -0.07
     Hoch
    -0.07
    EXTERN
    -0.07
     Fach
    -0.06
    �
    -0.06
    Integration
    -0.06
    isch
    -0.06
    agens
    -0.06
    POSITIVE LOGITS
     to
    0.09
     To
    0.08
     TO
    0.07
     duyg
    0.07
     Cross
    0.07
     hakk
    0.06
     cannot
    0.06
    Sid
    0.06
    To
    0.06
     plaintext
    0.06
    Act Density 0.016%

    No Known Activations