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

    Neuronpedia

    INDEX
    Explanations

    }}

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mass
    -0.06
    vlan
    -0.06
    @s
    -0.06
     ros
    -0.05
     مارس
    -0.05
     fundament
    -0.05
    CNT
    -0.05
    .minecraft
    -0.05
    Thr
    -0.05
     Giul
    -0.05
    POSITIVE LOGITS
    ODO
    0.08
    об
    0.07
     unmistak
    0.07
     Subjects
    0.07
     Coca
    0.07
    .asarray
    0.07
     Coverage
    0.07
     acuerdo
    0.07
     мона
    0.07
     Exclude
    0.07
    Act Density 0.009%

    No Known Activations