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

    Neuronpedia

    INDEX
    Explanations

    supportive conversations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     transient
    -0.08
     CL
    -0.08
     NH
    -0.08
     UT
    -0.07
    Hint
    -0.07
     klok
    -0.07
    EF
    -0.07
     automatic
    -0.07
     HAL
    -0.07
    Transient
    -0.07
    POSITIVE LOGITS
     восстановления
    0.09
    /support
    0.09
    壮
    0.08
     soutien
    0.08
     поддержку
    0.08
     chaleure
    0.08
     همراه
    0.08
     demeanor
    0.08
     cheering
    0.08
     переж
    0.08
    Act Density 0.017%

    No Known Activations